111 lines
4.2 KiB
Python
111 lines
4.2 KiB
Python
from typing import List, Tuple
|
|
|
|
import pytest
|
|
from transformers import AutoTokenizer
|
|
|
|
from vllm.config import VisionLanguageConfig
|
|
|
|
from ..conftest import IMAGE_FILES
|
|
|
|
pytestmark = pytest.mark.vlm
|
|
|
|
# The image token is placed before "user" on purpose so that the test can pass
|
|
HF_IMAGE_PROMPTS = [
|
|
"<image>\nUSER: What's the content of the image?\nASSISTANT:",
|
|
"<image>\nUSER: What is the season?\nASSISTANT:",
|
|
]
|
|
|
|
assert len(HF_IMAGE_PROMPTS) == len(IMAGE_FILES)
|
|
|
|
|
|
def iter_llava_configs(model_name: str):
|
|
image_hw_to_feature_size = {
|
|
(336, 336): 576,
|
|
}
|
|
|
|
for (h, w), f in image_hw_to_feature_size.items():
|
|
for input_type, input_shape in [
|
|
(VisionLanguageConfig.ImageInputType.PIXEL_VALUES, (1, 3, h, w)),
|
|
(VisionLanguageConfig.ImageInputType.IMAGE_FEATURES, (1, f, 1024)),
|
|
]:
|
|
yield (model_name,
|
|
VisionLanguageConfig(image_input_type=input_type,
|
|
image_feature_size=f,
|
|
image_token_id=32000,
|
|
image_input_shape=input_shape,
|
|
image_processor=model_name,
|
|
image_processor_revision=None))
|
|
|
|
|
|
model_and_vl_config = [
|
|
*iter_llava_configs("llava-hf/llava-1.5-7b-hf"),
|
|
]
|
|
|
|
|
|
def vllm_to_hf_output(vllm_output: Tuple[List[int], str],
|
|
vlm_config: VisionLanguageConfig, model_id: str):
|
|
"""Sanitize vllm output to be comparable with hf output.
|
|
The function reduces `input_ids` from 1, 32000, 32000, ..., 32000,
|
|
x1, x2, x3 ... to 1, 32000, x1, x2, x3 ...
|
|
It also reduces `output_str` from "<image><image>bla" to "bla".
|
|
"""
|
|
input_ids, output_str = vllm_output
|
|
image_token_id = vlm_config.image_token_id
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
|
image_token_str = tokenizer.decode(image_token_id)
|
|
|
|
hf_input_ids = [
|
|
input_id for idx, input_id in enumerate(input_ids)
|
|
if input_id != image_token_id or input_ids[idx - 1] != image_token_id
|
|
]
|
|
hf_output_str = output_str \
|
|
.replace(image_token_str * vlm_config.image_feature_size, "")
|
|
|
|
return hf_input_ids, hf_output_str
|
|
|
|
|
|
# TODO: Add test for `tensor_parallel_size` [ref: PR #3883]
|
|
@pytest.mark.parametrize("model_and_config", model_and_vl_config)
|
|
@pytest.mark.parametrize("dtype", ["half"])
|
|
@pytest.mark.parametrize("max_tokens", [128])
|
|
def test_models(hf_runner, vllm_runner, hf_images, vllm_images,
|
|
model_and_config, dtype: str, max_tokens: int) -> None:
|
|
"""Inference result should be the same between hf and vllm.
|
|
|
|
All the image fixtures for the test is under tests/images.
|
|
For huggingface runner, we provide the PIL images as input.
|
|
For vllm runner, we provide MultiModalData objects and corresponding
|
|
vision language config as input.
|
|
Note, the text input is also adjusted to abide by vllm contract.
|
|
The text output is sanitized to be able to compare with hf.
|
|
"""
|
|
model_id, vlm_config = model_and_config
|
|
|
|
with hf_runner(model_id, dtype=dtype, is_vision_model=True) as hf_model:
|
|
hf_outputs = hf_model.generate_greedy(HF_IMAGE_PROMPTS,
|
|
max_tokens,
|
|
images=hf_images)
|
|
|
|
vllm_image_prompts = [
|
|
p.replace("<image>", "<image>" * vlm_config.image_feature_size)
|
|
for p in HF_IMAGE_PROMPTS
|
|
]
|
|
|
|
with vllm_runner(model_id,
|
|
dtype=dtype,
|
|
enforce_eager=True,
|
|
**vlm_config.as_cli_args_dict()) as vllm_model:
|
|
vllm_outputs = vllm_model.generate_greedy(vllm_image_prompts,
|
|
max_tokens,
|
|
images=vllm_images)
|
|
|
|
for i in range(len(HF_IMAGE_PROMPTS)):
|
|
hf_output_ids, hf_output_str = hf_outputs[i]
|
|
vllm_output_ids, vllm_output_str = vllm_to_hf_output(
|
|
vllm_outputs[i], vlm_config, model_id)
|
|
assert hf_output_str == vllm_output_str, (
|
|
f"Test{i}:\nHF: {hf_output_str!r}\nvLLM: {vllm_output_str!r}")
|
|
assert hf_output_ids == vllm_output_ids, (
|
|
f"Test{i}:\nHF: {hf_output_ids}\nvLLM: {vllm_output_ids}")
|